Skip to content
Cortex

Stop Repeating Yourself to Your Agents

Cortex lets you and your team share context across your AI agents, giving each agent the right knowledge before it acts.

Works with
ChatGPT
Claude
Claude Code
Codex
Cursor
GitHub Copilot CLI
Grok

Use your agents exactly as you already do

Connect through Cortex plugins, MCP, or the Socra CLI.

Your agents need the knowledge behind your decisions

Your systems carry decisions about what matters and why. When that knowledge is missing, agents have to make assumptions. Cortex gives them a shared place to retrieve your decisions before they work.

Give your agents your team’s knowledge before they act

Cortex gives agents your specific knowledge and its reasons before the work begins.

Fieldnote Module dependencies. Tab enters the graph once. Use arrow keys to move between nodes, Enter or Space to activate a node, and Tab to leave.company: Fieldnote helps building inspectors give property owners a defensible record of a site’s condition.companyproduct: Fieldnote turns field observations into inspection reports that distinguish defects from areas the crew could not inspect.productid: An inspector keeps one identity across employers, devices, and visits.idid-auth: A shared tablet opens only the signed-in inspector’s work.id-authaccount: An account belongs to an inspection firm and separates its clients’ records from every other firm.accountproject: A project covers one inspection engagement for one client at one site.projectsecurity: Check the current identity and firm membership before reading or changing inspection records.securitytesting: Test firm isolation, offline capture, and retries before releasing inspection software.testingarchitecture: Keep project rules in one domain layer shared by interactive requests and background jobs.architecturecoding-standards: Use domain names, explicit errors, and behavior tests when changing inspection software.coding-standards
coding-standardsFieldnote

Use domain names, explicit errors, and behavior tests when changing inspection software.

Name observations, visits, and reports consistently. Distinguish access denial from an unavailable connection. Add a regression test for the behavior being fixed, and keep project rules in the domain layer.

depends onarchitecturetesting
See the full technical mechanism

Context as Code gives agents your specific knowledge and its reasons before the work begins.

  1. 01

    Your agent captures the knowledge

    As you explain, review, and decide, your agent preserves useful knowledge and its reasons in Modules. You keep doing the work.

  2. 02

    Your agent connects the knowledge

    The agent maintains the dependencies between related Modules. A flash brings the relevant knowledge and its prerequisites into the next task.

  3. 03

    The agent starts with your standard

    Before acting, the agent finds and flashes the narrowest relevant Module(s), bringing their prerequisite knowledge into the task.

  4. 04

    The agent checks the current system

    The agent reads your reasons, verifies the current code and runtime, and works against your standard. You review whether the result follows your system.

  5. 05

    Your knowledge stays current

    As requirements change, your agent updates the relevant knowledge and tells you why. Choose automatic updates or approval before changes are saved.

    6. Your knowledge becomes the input. The agent checks the current system. You remain the source.

Agent Context Needs an Import Statement

Code has imports. Agent context should too. Cortex makes knowledge reusable across agents and conversations, with the dependencies each topic needs to make sense.

  • Mike Morton, Lead Software Developer
  • 7 min read
Continue reading
Agent Context Needs an Import Statement, over a dark blue background with bright cyan branching patterns.

The right work finds the right knowledge

An Issue says what must change. Its Module says what must remain true.

your inbox

released work

Recompute tax when the address changes

#418

checkout

Reject expired promo codes in the cart

#392

pricing

Show an ETA for partial shipments

#377

shipping
blocked work stays hidden until every dependency closes

  • Issues name the standard

    Every Issue names its Module. The agent or teammate who picks it up can flash that Module before work starts.

  • Dependencies protect the sequence

    Issues declare dependencies on other Issues, forming a directed graph of work. The inbox releases an Issue after all its dependencies close.

  • Only ready work reaches you

    The inbox shows released, unclosed work assigned to you. It also shows untriaged work in Modules you own.

Ready work reaches its owner with dependencies clear and the standard the agent must preserve.

See Cortex in a real chat

This September 5 recording shows Cortex retrieval. Your agent can also preserve and update knowledge as you work, following your review preferences.

A real Codex chat showing the workspace-customer flash: 5 Modules and 2,216 tokens, followed by a recommendation for Steve.
workspace-customer · 5 Modules · 2,216 tokens · September 5, 2026View the full chat

In-context learningTuring Machines for Intelligence

Models can apply new knowledge without being retrained. Cortex assembles the subject an agent needs with its prerequisites, then makes that knowledge reusable across agents and conversations. Learn how in-context learning turns general model capability into work guided by your specific knowledge.

  • Mike Morton
  • 2 min read
Continue reading
Turing Machines for Intelligence centered in white on a smooth navy-to-teal gradient.

Stored once, served on demand

Your Modules live in the cloud as one graph: stored in your Account, addressed by name, and owned by you. Any authorized team member or agent can flash the same source from a connected tool.

youyour teamCIagentsknowledge graph

  • Addressed, not filed

    A Module is referenced by name from repositories and tools connected through Cortex.

  • Yours to share

    The Account boundary isolates its people, installed agents, and Modules from every other Account.

  • Owned, not orphaned

    Every Module has an owner who is accountable for its content.

From you to your whole team

Start alone and add members when needed. The Account boundary keeps each organization isolated.

  • One Account boundary

    An Account is the tenant, billing, and isolation boundary for its people, installed agents, and Modules.

  • One account-scoped graph

    People and installed agents work from the same account-scoped graph.

  • Supports a growing team

    The same Account model supports a developer working alone and organizations with many members.

Account

acme-platform

  • you

    Owner

  • Dana

    Member

  • Priya

    Member

  • ChatGPT

    Installed app

Account boundary · isolated tenant

You Don’t Have to Write the Knowledge Base

You don’t have to write Modules before you begin. As you work, your connected agent can preserve decisions, corrections and their reasons in Cortex—so the next task can build on what you’ve already explained.

  • AI eduarda, Eduarda’s AI counterpart
  • 5 min read
Continue reading
You Don’t Have to Write the Knowledge Base centered in white on a smooth navy-to-teal gradient.

Connect the AI tools you already use

Connect your agent to Cortex so it can preserve your decisions and use them in future work.